cc-claw 0.4.4 → 0.4.6
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +6 -3
- package/dist/cli.js +675 -204
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -15,7 +15,7 @@ Send text, voice, photos, documents, or videos. Switch backends with `/claude`,
|
|
|
15
15
|
- **Agent templates** — Define reusable agent personas as markdown files (`~/.cc-claw/agents/*.md`). Security reviewers, content writers, researchers — spawn them by name.
|
|
16
16
|
- **Scheduling** — Cron jobs, one-shot tasks, and intervals. Per-job backend, model, and delivery (Telegram, webhook, or silent).
|
|
17
17
|
- **Memory** — Hybrid vector + keyword search. The agent remembers what you tell it across sessions, with salience decay.
|
|
18
|
-
- **Voice** — Send voice messages, get voice replies. Groq Whisper for transcription
|
|
18
|
+
- **Voice** — Send voice messages, get voice replies. Groq Whisper for transcription. Choose from ElevenLabs, Grok (xAI), or macOS for synthesis.
|
|
19
19
|
- **50+ CLI commands** — Full system management from terminal. Every command supports `--json` for scripting.
|
|
20
20
|
- **MCP support** — Model Context Protocol servers extend the agent with external tools and data.
|
|
21
21
|
- **Cross-channel awareness** — Actions from CLI are visible to Telegram and vice versa via the activity log.
|
|
@@ -166,6 +166,8 @@ Read commands work offline (direct DB access). Write commands require the daemon
|
|
|
166
166
|
| `/permissions` | Permission mode (yolo/safe/readonly/plan) |
|
|
167
167
|
| `/tools` | Configure allowed tools |
|
|
168
168
|
| `/voice` | Toggle voice replies |
|
|
169
|
+
| `/voice_config` | Configure voice provider and voice |
|
|
170
|
+
| `/response_style` | Set the AI response style (concise/normal/detailed) |
|
|
169
171
|
| `/verbose` | Tool visibility level |
|
|
170
172
|
| `/limits` | Usage limits per backend |
|
|
171
173
|
|
|
@@ -186,7 +188,7 @@ Read commands work offline (direct DB access). Write commands require the daemon
|
|
|
186
188
|
```
|
|
187
189
|
Telegram → TelegramChannel → router (handleMessage)
|
|
188
190
|
├── command → handleCommand
|
|
189
|
-
├── voice → Groq Whisper STT → askAgent
|
|
191
|
+
├── voice → Groq Whisper STT → askAgent → TTS (ElevenLabs/Grok/macOS)
|
|
190
192
|
├── photo/document/video → handleMedia → askAgent
|
|
191
193
|
└── text → askAgent → sendResponse
|
|
192
194
|
└── [SEND_FILE:/path] → channel.sendFile
|
|
@@ -251,7 +253,8 @@ Set in `~/.cc-claw/.env` (created by `cc-claw setup`):
|
|
|
251
253
|
| `CLOUD_ML_REGION` | For Claude | e.g., `us-east5` |
|
|
252
254
|
| `ANTHROPIC_VERTEX_PROJECT_ID` | For Claude | GCP project ID |
|
|
253
255
|
| `GROQ_API_KEY` | No | Voice transcription |
|
|
254
|
-
| `ELEVENLABS_API_KEY` | No | Voice replies |
|
|
256
|
+
| `ELEVENLABS_API_KEY` | No | Voice replies (ElevenLabs) |
|
|
257
|
+
| `XAI_API_KEY` | No | Voice replies (Grok/xAI) |
|
|
255
258
|
| `GEMINI_API_KEY` | No | Video analysis |
|
|
256
259
|
| `DASHBOARD_ENABLED` | No | `1` for web dashboard on port 3141 |
|
|
257
260
|
| `EMBEDDING_PROVIDER` | No | `ollama` (default), `gemini`, `openai`, `off` |
|